INDEX

Explanations

specific lessons or instructional content within a text

oai_token-act-pair · gpt-4o-mini Triggered by @bot

list items

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 betweenstory

-0.56

 disponibilités

-0.50

 &___

-0.50



-0.47

 NgModule

-0.46

ArgsConstructor

-0.45

RegressionTest

-0.45

:✨

-0.44

tagHelperRunner

-0.43

Hochspringen

-0.42

POSITIVE LOGITS

 للاسماء

0.48

 nakalista

0.44

 nahilalakip

0.39

RotationOrder

0.38

mögens

0.38

linkedin

0.35

SOA

0.35

derung

0.34

uns

0.33

riebene

0.33

Activations Density 0.061%

specific lessons or instructional content within a text

list items

No Comments

No Known Activations